Knowledge graph (KG) embedding is a fundamental task in natural language processing, and various methods have been proposed to explore semantic patterns in distinctive ways. In this paper, we propose to learn an ensemble by leveraging existing methods in a relation-aware manner. However, exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods. To address this issue, we propose a divide-search-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently. This algorithm has the same computation cost as general ensemble methods but with much better performance. Experimental results on benchmark datasets demonstrate the effectiveness of the proposed method in efficiently searching relation-aware ensemble weights and achieving state-of-the-art embedding performance. The code is public at https://github.com/LARS-research/RelEns.

翻译：知识图谱嵌入是自然语言处理中的基础任务,已有多种方法被提出,以不同方式探索语义模式。本文提出利用现有方法以关系感知的方式进行集成学习。然而,通过关系感知集成探索这些语义会导致比通用集成方法更大的搜索空间。为解决该问题,我们提出分而治之的搜索组合算法RelEns-DSC,该算法独立搜索关系维度的集成权重。该算法与通用集成方法具有相同的计算成本,但性能显著更优。在基准数据集上的实验结果表明,所提方法能高效搜索关系感知集成权重,并取得最先进的嵌入性能。代码已开源在https://github.com/LARS-research/RelEns。